© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82247
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic and creative disciplines or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auer
    -0.09
    à¸Ńà¸ļ
    -0.08
    Å¡ak
    -0.08
    ISCO
    -0.08
    lej
    -0.07
    ORMAL
    -0.07
    -LAST
    -0.07
    asje
    -0.07
    ึà¸ģ
    -0.07
    chten
    -0.07
    POSITIVE LOGITS
    0.06
     director
    0.06
    PU
    0.06
    /runtime
    0.06
    aset
    0.06
     prom
    0.06
     ES
    0.05
    -direction
    0.05
    618
    0.05
    emma
    0.05
    Activations Density 0.017%

    No Known Activations